DiffNorm: Self-Supervised Normalization for Non-autoregressive Speech-to-speech Translation
This work addresses speech-to-speech translation for faster and more coherent outputs, but it is incremental as it builds on existing non-autoregressive methods.
The paper tackled the problem of incoherent and repetitive outputs in non-autoregressive speech-to-speech translation by introducing DiffNorm, a diffusion-based normalization strategy, and classifier-free guidance, resulting in improvements of about +7 ASR-BLEU for English-Spanish and +2 ASR-BLEU for English-French translations with significant speedups.
Non-autoregressive Transformers (NATs) are recently applied in direct speech-to-speech translation systems, which convert speech across different languages without intermediate text data. Although NATs generate high-quality outputs and offer faster inference than autoregressive models, they tend to produce incoherent and repetitive results due to complex data distribution (e.g., acoustic and linguistic variations in speech). In this work, we introduce DiffNorm, a diffusion-based normalization strategy that simplifies data distributions for training NAT models. After training with a self-supervised noise estimation objective, DiffNorm constructs normalized target data by denoising synthetically corrupted speech features. Additionally, we propose to regularize NATs with classifier-free guidance, improving model robustness and translation quality by randomly dropping out source information during training. Our strategies result in a notable improvement of about +7 ASR-BLEU for English-Spanish (En-Es) and +2 ASR-BLEU for English-French (En-Fr) translations on the CVSS benchmark, while attaining over 14x speedup for En-Es and 5x speedup for En-Fr translations compared to autoregressive baselines.